Abstract
FPGA (Field Programmable Gate Arrays) implementation of an off-line handwritten digit recognition system based on elastic meshing directional feature extraction and integrated neural network classifier is proposed in this paper. Elastic meshing directional feature extraction is used to extract the feature of normalized 32*16 handwritten digit images. Integrated neural network classifier with BP (back-propagation) learning algorithm is designed as classifier. The pipeline technology and multi-buffer technology are used in the FPGA implementation of elastic meshing directional feature extraction. FPGA implementation architecture of neural network computing unit and integrated neural network classifier is proposed in this paper. Experiment shows that compared with software-based implementation, FPGA-based system can greatly speed up off-line handwritten digit recognition and is suitable for application in some real-time situations where high process speed and portability are required.
Project sponsored by:NSFC(No.60275005), GDNSF(No.2003C50101, 011611).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Athanas, P., Abbott, L., Cherbaka, M., Pudipeddi, B., Paar, K.: A Custom Computing Solution to Automated Visual Inspection of Silicon Wafers. In: Proceedings of Southeastcon 1997, ’Engineering New Century’, pp. 315–319. IEEE, Los Alamitos (1997)
Jean, J., Liang, X., Drozd, B., Tomko, K.: Accelerating an IR Automatic Target Recognition Application with FPGAs. In: Proceedings of Seventh Annual IEEE Symposium on Field-Programmable Custom Computing Machines, FCCM 1999, pp. 290–291 (1999)
Miteran, J., Bailly, R., Gorria, P.: Real Time Image Segmentation Using FPGA and Parallel Processor. In: Proceedings of 1996 IEEE TENCON. Digital Signal Processing Applications, TENCON 1996, vol. 1, pp. 233–236 (1996)
Jin, L., Xu, B.: Directional Cellular Feature Extraction with Elastic Meshing for Handwritten Chinese Character Recognition. Journal of Circuits and Systems 2, 7–12 (1997)
Luo, X., Dong, S., Jin, L., Xu, H.: An Integrated Neural Network Based Classifier for Handwritten Digit Recognition. Computer Engineering 28(8), 69–71 (2002)
Gao, Y., Zhang, L., Wu, G.: An Algorithm for Threshold Based on Arithmetic Mean of Gray. Journal of Image and Graphics Value 4, 524–528 (1999)
Ma, X., Jin, L., Shen, D., Yin, J.: A Mixed Parallel Neural Network Computing Unit Implementation in FPGA. In: IEEE Int. Conf. Neural Networks & Signal Processing, Nanjing, China (2003)
Wang, Y., Zhang, Z.: VHDL Programming and Simulation. Posts & Telecom Press, Beijing (2000)
Piche, S.W.: The Selection of Weight Accuracies for Madalines Neural Networks. IEEE Transactions on 6(2), 432–445 (1995)
Wang, C., Xue, X., Zhong, X.: The Way of Using FPGA/CPLD Design Tool Xilinx ISE 5.X, pp. 85–160. Posts & Telecom Press, Beijing (2003)
Wang, J., Yang, J.: Digial System Design and Verilog HDL, 1st edn., pp. 51–62. Publishing House of Electronics Industry, Beijing (2002)
Chen, X., Teng, L.: Starting VHDL and Its Application, pp. 165–192. Posts & Telecom Press, Beijing (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Shen, D., Jin, L., Ma, X. (2004). FPGA Implementation of Feature Extraction and Neural Network Classifier for Handwritten Digit Recognition. In: Yin, FL., Wang, J., Guo, C. (eds) Advances in Neural Networks – ISNN 2004. ISNN 2004. Lecture Notes in Computer Science, vol 3173. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-28647-9_163
Download citation
DOI: https://doi.org/10.1007/978-3-540-28647-9_163
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22841-7
Online ISBN: 978-3-540-28647-9
eBook Packages: Springer Book Archive